Multi-Layer Modeling of Dense Vegetation from Aerial LiDAR Scans

@article{Kalinicheva2022MultiLayerMO,
  title={Multi-Layer Modeling of Dense Vegetation from Aerial LiDAR Scans},
  author={Ekaterina Kalinicheva and Loic Landrieu and Cl{\'e}ment Mallet and Nesrine Chehata},
  journal={2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2022},
  pages={1341-1350}
}
The analysis of the multi-layer structure of wild forests is an important challenge of automated large-scale forestry. While modern aerial LiDARs offer geometric information across all vegetation layers, most datasets and methods focus only on the segmentation and reconstruction of the top of canopy. We release WildForest3D, which consists of 29 study plots and over 2000 individual trees across 47 000m2 with dense 3D annotation, along with occupancy and height maps for 3 vegetation layers… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 47 REFERENCES

Vegetation Stratum Occupancy Prediction from Airborne LiDAR 3D Point Clouds

TLDR
This work proposes a 3D deep learning method to estimate the occupancy of different vegetation strata from airborne LiDAR and camera sensors and predicts raster occupancy maps for three vegetationstrata (lower, medium, and higher) from 3D point clouds.

3-D mapping of a multi-layered Mediterranean forest using ALS data

Canopy Density Model: A New ALS-Derived Product to Generate Multilayer Crown Cover Maps

The canopy density model (CDM), a new product interpolated from airborne laser scanner (ALS) data and dedicated to forest structure characterization is presented. It exploits both the multiecho

Predicting Vegetation Stratum Occupancy from Airborne LiDAR Data with Deep Learning

Estimating over- and understorey canopy density of temperate mixed stands by airborne LiDAR data

Estimating forest structural attributes is one of the essential forestry-related remote sensing applications. The methods applied so far typically concentrate on the structure of the overstorey. For

Forest understory trees can be segmented accurately within sufficiently dense airborne laser scanning point clouds

TLDR
It is shown that at a density of ~170 pt/m² understory trees can likely be segmented as accurately as overstory trees, given the advancements of LiDAR sensor technology, point clouds will affordably reach this required density.

A robust approach for tree segmentation in deciduous forests using small-footprint airborne LiDAR data

Synthesizing Disparate LiDAR and Satellite Datasets through Deep Learning to Generate Wall-to-Wall Regional Inventories for the Complex, Mixed-Species Forests of the Eastern United States

TLDR
This work presents a model using a 3-D convolutional neural network (CNN), a form of deep learning capable of scanning a LiDAR point cloud, combined with coincident satellite data (spectral, phenology, and disturbance history), which shows promise for improving the prediction of forest attributes from regional LiDar data and for combining disparateLiDAR datasets into a common framework for large-scale estimation.

Airborne Lidar Estimation of Aboveground Forest Biomass in the Absence of Field Inventory

TLDR
Results over 40 plots of a multilayered forest show that the lidar method provides AGB estimates with a relatively small random error and bias, and provides local AGB baselines that meet the requirements in terms of accuracy to calibrate satellite remote sensing measurements.

Modelling vegetation understory cover using LiDAR metrics

TLDR
The best approach to predict understory structure is using the mixed-effects model with the voxel-based understory LiDAR metric along with vertical stratum, but that other understoryLiDAR metrics (fractional cover, normalized cover and leaf area density) would still be effective in mixed- effects and Random Forest modelling approaches.